Evolving Dexterous Robots from Scratch

2026-09-27

AI Summary

This work addresses the reliance of dexterous manipulation robots on manual design and their confinement to biomimetic structures by proposing a framework for autonomously evolving free-form robots from scratch. Methodologically, it discards predefined geometric and joint assumptions, integrating contrastive learning to construct a highly searchable genetic embedding space. This is coupled with an autoregressive developmental model for decoding, evolutionary strategies for selection, and reinforcement learning for control policy training. The project achieves a fully automated, zero-shot closed-loop pipeline spanning digital design to physical fabrication. It attains state-of-the-art performance in capability, diversity, and complexity, successfully translating evolved designs into manufacturable blueprints validated through real-world hardware experiments.

Abstract

Little is known about how to manually design agents capable of dexterous manipulation. Some design principles have been inferred from close examination of how animals manipulate objects, but these structures and behaviors have so far resisted biomimicry and may not be optimal for artificial machines. Here we evolve freeform robots to pick up, hold, rotate, and use diverse objects. Unlike other approaches to optimizing robot hands, we do not presuppose the presence, articulation, or geometry of any part of the body. Although familiar prehensile forms such as tails, beaks, paws and claws may emerge spontaneously under certain conditions--and while such conditions could be of interest to evolutionary biologists--de novo manipulator design can also reveal whole new solutions, overlooked or unknown structures which may be better suited for the task at hand. We use contrastive learning to create a highly searchable genetic embedding of design space, an autoregressive developmental model to decode designs, evolutionary strategies to find good designs, and reinforcement learning to train each evolved design. Winning designs were automatically converted into a manufacturable blueprint, printed, assembled and tested in the real world in a zero-shot manner. The results represent the state-of-the-art in evolutionary robotics in terms of performance, diversity and complexity.

Problem

• dexterous manipulation
• evolutionary robotics
• de novo design
• freeform robots

Innovation

• Evolutionary Robotics
• Contrastive Learning
• Reinforcement Learning
• Dexterous Manipulation
• Zero-shot Transfer